tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

Vulkan: Add DP4A MMQ and Q8_1 quantization shader (#12135)

Browse Source 
* Vulkan: Add DP4A MMQ and Q8_1 quantization shader

* Add q4_0 x q8_1 matrix matrix multiplication support

* Vulkan: Add int8 coopmat MMQ support

* Vulkan: Add q4_1, q5_0 and q5_1 quants, improve integer dot code

* Add GL_EXT_integer_dot_product check

* Remove ggml changes, fix mmq pipeline picker

* Remove ggml changes, restore Intel coopmat behaviour

* Fix glsl compile attempt when integer vec dot is not supported

* Remove redundant code, use non-saturating integer dot, enable all matmul sizes for mmq

* Remove redundant comment

* Fix integer dot check

* Fix compile issue with unsupported int dot glslc

* Update Windows build Vulkan SDK version
This commit is contained in:
0cc4m
2025-03-31 14:37:01 +02:00
committed by GitHub
parent 1790e73157
commit a8a1f33567
10 changed files with 1146 additions and 95 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.github/workflows/build.yml vendored
View File

@ -803,7 +803,7 @@ jobs:
env:
OPENBLAS_VERSION: 0.3.23
SDE_VERSION: 9.33.0-2024-01-07
VULKAN_VERSION: 1.4.304.1
VULKAN_VERSION: 1.4.309.0
strategy:
matrix: